ru-dalle
ru-dalle copied to clipboard
ImageNet classification with ru-dalle?
Hi Team, Thanks for the excellent contribution to open source. I've been trying to adapt your code. I'm mostly focused on getting image embeddings from the given image and train a classifier on top of it. I guess dalle code is composed on text and image embeddings. Any direction on generation image feature vector, what part of code I should modify?
Any help would be greatly appreciated.
Thanks.
You can try to use vqgan image encoder and mlp head for classification. but better to use VIT/RN50 and other
Thanks for the response. I just want to check ru-dalle's image encoder performance on zero shot image classification.